Pull request

* Copy offloading for qemu-img convert (iSCSI, raw, and qcow2)
 
    If the underlying storage supports copy offloading, qemu-img convert will
    use it instead of performing reads and writes.  This avoids data transfers
    and thus frees up storage bandwidth for other purposes.  SCSI EXTENDED COPY
    and Linux copy_file_range(2) are used to implement this optimization.
 
  * Drop spurious "WARNING: I\/O thread spun for 1000 iterations" warning
 -----BEGIN PGP SIGNATURE-----
 
 iQEcBAABAgAGBQJbFSBoAAoJEJykq7OBq3PISpEIAIcMao4/rzinAWXzS+ncK9LO
 6FtRVpgutpHaWX2ayySaz5n2CdR3cNMrpCI7sjY2Kw0lrdkqxPgl5n0SWD+VCl4W
 7+JLz/uF0iUV8X+99e7WGAjZbm9LSlxgn5AQKfrrwyPf0ZfzoYQ5nBMcQ6xjEeQP
 48j2WqJqN9/u8RBD07o11yn0+CE5g56/f12xVjR5ASVodzsAmcZ2OQRMQbM01isU
 1mBekJQkDxJkt5l13Rql8+t+vWz8/9BEW2c/eIDKvoayMqYJpdfKv4DqLloIuHnc
 3RkquA0zUuKtl7xEnEkH/We7fi4QPGW/vyBN7ychS/zKzZFQrXmwqrAuFSw3dKU=
 =vZp+
 -----END PGP SIGNATURE-----

Merge remote-tracking branch 'remotes/stefanha/tags/block-pull-request' into staging

Pull request

 * Copy offloading for qemu-img convert (iSCSI, raw, and qcow2)

   If the underlying storage supports copy offloading, qemu-img convert will
   use it instead of performing reads and writes.  This avoids data transfers
   and thus frees up storage bandwidth for other purposes.  SCSI EXTENDED COPY
   and Linux copy_file_range(2) are used to implement this optimization.

 * Drop spurious "WARNING: I\/O thread spun for 1000 iterations" warning

# gpg: Signature made Mon 04 Jun 2018 12:20:08 BST
# gpg:                using RSA key 9CA4ABB381AB73C8
# gpg: Good signature from "Stefan Hajnoczi <stefanha@redhat.com>"
# gpg:                 aka "Stefan Hajnoczi <stefanha@gmail.com>"
# Primary key fingerprint: 8695 A8BF D3F9 7CDA AC35  775A 9CA4 ABB3 81AB 73C8

* remotes/stefanha/tags/block-pull-request:
  main-loop: drop spin_counter
  qemu-img: Convert with copy offloading
  block-backend: Add blk_co_copy_range
  iscsi: Implement copy offloading
  iscsi: Create and use iscsi_co_wait_for_task
  iscsi: Query and save device designator when opening
  file-posix: Implement bdrv_co_copy_range
  qcow2: Implement copy offloading
  raw: Implement copy offloading
  raw: Check byte range uniformly
  block: Introduce API for copy offloading

Signed-off-by: Peter Maydell <peter.maydell@linaro.org>

block/block-backend.c

@@ -2211,3 +2211,21 @@ void blk_unregister_buf(BlockBackend *blk, void *host)
 {
     bdrv_unregister_buf(blk_bs(blk), host);
 }
+
+int coroutine_fn blk_co_copy_range(BlockBackend *blk_in, int64_t off_in,
+                                   BlockBackend *blk_out, int64_t off_out,
+                                   int bytes, BdrvRequestFlags flags)
+{
+    int r;
+    r = blk_check_byte_request(blk_in, off_in, bytes);
+    if (r) {
+        return r;
+    }
+    r = blk_check_byte_request(blk_out, off_out, bytes);
+    if (r) {
+        return r;
+    }
+    return bdrv_co_copy_range(blk_in->root, off_in,
+                              blk_out->root, off_out,
+                              bytes, flags);
+}

block/file-posix.c

@@ -59,6 +59,7 @@
 #ifdef __linux__
 #include <sys/ioctl.h>
 #include <sys/param.h>
+#include <sys/syscall.h>
 #include <linux/cdrom.h>
 #include <linux/fd.h>
 #include <linux/fs.h>
@@ -187,6 +188,8 @@ typedef struct RawPosixAIOData {
 #define aio_ioctl_cmd   aio_nbytes /* for QEMU_AIO_IOCTL */
     off_t aio_offset;
     int aio_type;
+    int aio_fd2;
+    off_t aio_offset2;
 } RawPosixAIOData;
 
 #if defined(__FreeBSD__) || defined(__FreeBSD_kernel__)
@@ -1446,6 +1449,49 @@ static ssize_t handle_aiocb_write_zeroes(RawPosixAIOData *aiocb)
     return -ENOTSUP;
 }
 
+#ifndef HAVE_COPY_FILE_RANGE
+static off_t copy_file_range(int in_fd, off_t *in_off, int out_fd,
+                             off_t *out_off, size_t len, unsigned int flags)
+{
+#ifdef __NR_copy_file_range
+    return syscall(__NR_copy_file_range, in_fd, in_off, out_fd,
+                   out_off, len, flags);
+#else
+    errno = ENOSYS;
+    return -1;
+#endif
+}
+#endif
+
+static ssize_t handle_aiocb_copy_range(RawPosixAIOData *aiocb)
+{
+    uint64_t bytes = aiocb->aio_nbytes;
+    off_t in_off = aiocb->aio_offset;
+    off_t out_off = aiocb->aio_offset2;
+
+    while (bytes) {
+        ssize_t ret = copy_file_range(aiocb->aio_fildes, &in_off,
+                                      aiocb->aio_fd2, &out_off,
+                                      bytes, 0);
+        if (ret == -EINTR) {
+            continue;
+        }
+        if (ret < 0) {
+            if (errno == ENOSYS) {
+                return -ENOTSUP;
+            } else {
+                return -errno;
+            }
+        }
+        if (!ret) {
+            /* No progress (e.g. when beyond EOF), fall back to buffer I/O. */
+            return -ENOTSUP;
+        }
+        bytes -= ret;
+    }
+    return 0;
+}
+
 static ssize_t handle_aiocb_discard(RawPosixAIOData *aiocb)
 {
     int ret = -EOPNOTSUPP;
@@ -1526,6 +1572,9 @@ static int aio_worker(void *arg)
     case QEMU_AIO_WRITE_ZEROES:
         ret = handle_aiocb_write_zeroes(aiocb);
         break;
+    case QEMU_AIO_COPY_RANGE:
+        ret = handle_aiocb_copy_range(aiocb);
+        break;
     default:
         fprintf(stderr, "invalid aio request (0x%x)\n", aiocb->aio_type);
         ret = -EINVAL;
@@ -1536,9 +1585,10 @@ static int aio_worker(void *arg)
     return ret;
 }
 
-static int paio_submit_co(BlockDriverState *bs, int fd,
+static int paio_submit_co_full(BlockDriverState *bs, int fd,
-                          int64_t offset, QEMUIOVector *qiov,
+                               int64_t offset, int fd2, int64_t offset2,
-                          int bytes, int type)
+                               QEMUIOVector *qiov,
+                               int bytes, int type)
 {
     RawPosixAIOData *acb = g_new(RawPosixAIOData, 1);
     ThreadPool *pool;
@@ -1546,6 +1596,8 @@ static int paio_submit_co(BlockDriverState *bs, int fd,
     acb->bs = bs;
     acb->aio_type = type;
     acb->aio_fildes = fd;
+    acb->aio_fd2 = fd2;
+    acb->aio_offset2 = offset2;
 
     acb->aio_nbytes = bytes;
     acb->aio_offset = offset;
@@ -1561,6 +1613,13 @@ static int paio_submit_co(BlockDriverState *bs, int fd,
     return thread_pool_submit_co(pool, aio_worker, acb);
 }
 
+static inline int paio_submit_co(BlockDriverState *bs, int fd,
+                                 int64_t offset, QEMUIOVector *qiov,
+                                 int bytes, int type)
+{
+    return paio_submit_co_full(bs, fd, offset, -1, 0, qiov, bytes, type);
+}
+
 static BlockAIOCB *paio_submit(BlockDriverState *bs, int fd,
         int64_t offset, QEMUIOVector *qiov, int bytes,
         BlockCompletionFunc *cb, void *opaque, int type)
@@ -2451,6 +2510,35 @@ static void raw_abort_perm_update(BlockDriverState *bs)
     raw_handle_perm_lock(bs, RAW_PL_ABORT, 0, 0, NULL);
 }
 
+static int coroutine_fn raw_co_copy_range_from(BlockDriverState *bs,
+                                               BdrvChild *src, uint64_t src_offset,
+                                               BdrvChild *dst, uint64_t dst_offset,
+                                               uint64_t bytes, BdrvRequestFlags flags)
+{
+    return bdrv_co_copy_range_to(src, src_offset, dst, dst_offset, bytes, flags);
+}
+
+static int coroutine_fn raw_co_copy_range_to(BlockDriverState *bs,
+                                             BdrvChild *src, uint64_t src_offset,
+                                             BdrvChild *dst, uint64_t dst_offset,
+                                             uint64_t bytes, BdrvRequestFlags flags)
+{
+    BDRVRawState *s = bs->opaque;
+    BDRVRawState *src_s;
+
+    assert(dst->bs == bs);
+    if (src->bs->drv->bdrv_co_copy_range_to != raw_co_copy_range_to) {
+        return -ENOTSUP;
+    }
+
+    src_s = src->bs->opaque;
+    if (fd_open(bs) < 0 || fd_open(bs) < 0) {
+        return -EIO;
+    }
+    return paio_submit_co_full(bs, src_s->fd, src_offset, s->fd, dst_offset,
+                               NULL, bytes, QEMU_AIO_COPY_RANGE);
+}
+
 BlockDriver bdrv_file = {
     .format_name = "file",
     .protocol_name = "file",
@@ -2474,6 +2562,8 @@ BlockDriver bdrv_file = {
     .bdrv_co_pwritev        = raw_co_pwritev,
     .bdrv_aio_flush = raw_aio_flush,
     .bdrv_aio_pdiscard = raw_aio_pdiscard,
+    .bdrv_co_copy_range_from = raw_co_copy_range_from,
+    .bdrv_co_copy_range_to  = raw_co_copy_range_to,
     .bdrv_refresh_limits = raw_refresh_limits,
     .bdrv_io_plug = raw_aio_plug,
     .bdrv_io_unplug = raw_aio_unplug,
@@ -2952,6 +3042,8 @@ static BlockDriver bdrv_host_device = {
     .bdrv_co_pwritev        = raw_co_pwritev,
     .bdrv_aio_flush	= raw_aio_flush,
     .bdrv_aio_pdiscard   = hdev_aio_pdiscard,
+    .bdrv_co_copy_range_from = raw_co_copy_range_from,
+    .bdrv_co_copy_range_to  = raw_co_copy_range_to,
     .bdrv_refresh_limits = raw_refresh_limits,
     .bdrv_io_plug = raw_aio_plug,
     .bdrv_io_unplug = raw_aio_unplug,

block/io.c

@@ -2835,3 +2835,100 @@ void bdrv_unregister_buf(BlockDriverState *bs, void *host)
         bdrv_unregister_buf(child->bs, host);
     }
 }
+
+static int coroutine_fn bdrv_co_copy_range_internal(BdrvChild *src,
+                                                    uint64_t src_offset,
+                                                    BdrvChild *dst,
+                                                    uint64_t dst_offset,
+                                                    uint64_t bytes,
+                                                    BdrvRequestFlags flags,
+                                                    bool recurse_src)
+{
+    int ret;
+
+    if (!src || !dst || !src->bs || !dst->bs) {
+        return -ENOMEDIUM;
+    }
+    ret = bdrv_check_byte_request(src->bs, src_offset, bytes);
+    if (ret) {
+        return ret;
+    }
+
+    ret = bdrv_check_byte_request(dst->bs, dst_offset, bytes);
+    if (ret) {
+        return ret;
+    }
+    if (flags & BDRV_REQ_ZERO_WRITE) {
+        return bdrv_co_pwrite_zeroes(dst, dst_offset, bytes, flags);
+    }
+
+    if (!src->bs->drv->bdrv_co_copy_range_from
+        || !dst->bs->drv->bdrv_co_copy_range_to
+        || src->bs->encrypted || dst->bs->encrypted) {
+        return -ENOTSUP;
+    }
+    if (recurse_src) {
+        return src->bs->drv->bdrv_co_copy_range_from(src->bs,
+                                                     src, src_offset,
+                                                     dst, dst_offset,
+                                                     bytes, flags);
+    } else {
+        return dst->bs->drv->bdrv_co_copy_range_to(dst->bs,
+                                                   src, src_offset,
+                                                   dst, dst_offset,
+                                                   bytes, flags);
+    }
+}
+
+/* Copy range from @src to @dst.
+ *
+ * See the comment of bdrv_co_copy_range for the parameter and return value
+ * semantics. */
+int coroutine_fn bdrv_co_copy_range_from(BdrvChild *src, uint64_t src_offset,
+                                         BdrvChild *dst, uint64_t dst_offset,
+                                         uint64_t bytes, BdrvRequestFlags flags)
+{
+    return bdrv_co_copy_range_internal(src, src_offset, dst, dst_offset,
+                                       bytes, flags, true);
+}
+
+/* Copy range from @src to @dst.
+ *
+ * See the comment of bdrv_co_copy_range for the parameter and return value
+ * semantics. */
+int coroutine_fn bdrv_co_copy_range_to(BdrvChild *src, uint64_t src_offset,
+                                       BdrvChild *dst, uint64_t dst_offset,
+                                       uint64_t bytes, BdrvRequestFlags flags)
+{
+    return bdrv_co_copy_range_internal(src, src_offset, dst, dst_offset,
+                                       bytes, flags, false);
+}
+
+int coroutine_fn bdrv_co_copy_range(BdrvChild *src, uint64_t src_offset,
+                                    BdrvChild *dst, uint64_t dst_offset,
+                                    uint64_t bytes, BdrvRequestFlags flags)
+{
+    BdrvTrackedRequest src_req, dst_req;
+    BlockDriverState *src_bs = src->bs;
+    BlockDriverState *dst_bs = dst->bs;
+    int ret;
+
+    bdrv_inc_in_flight(src_bs);
+    bdrv_inc_in_flight(dst_bs);
+    tracked_request_begin(&src_req, src_bs, src_offset,
+                          bytes, BDRV_TRACKED_READ);
+    tracked_request_begin(&dst_req, dst_bs, dst_offset,
+                          bytes, BDRV_TRACKED_WRITE);
+
+    wait_serialising_requests(&src_req);
+    wait_serialising_requests(&dst_req);
+    ret = bdrv_co_copy_range_from(src, src_offset,
+                                  dst, dst_offset,
+                                  bytes, flags);
+
+    tracked_request_end(&src_req);
+    tracked_request_end(&dst_req);
+    bdrv_dec_in_flight(src_bs);
+    bdrv_dec_in_flight(dst_bs);
+    return ret;
+}

block/iscsi.c

@@ -68,6 +68,7 @@ typedef struct IscsiLun {
     QemuMutex mutex;
     struct scsi_inquiry_logical_block_provisioning lbp;
     struct scsi_inquiry_block_limits bl;
+    struct scsi_inquiry_device_designator *dd;
     unsigned char *zeroblock;
     /* The allocmap tracks which clusters (pages) on the iSCSI target are
      * allocated and which are not. In case a target returns zeros for
@@ -555,6 +556,17 @@ static inline bool iscsi_allocmap_is_valid(IscsiLun *iscsilun,
                                offset / iscsilun->cluster_size) == size);
 }
 
+static void coroutine_fn iscsi_co_wait_for_task(IscsiTask *iTask,
+                                                IscsiLun *iscsilun)
+{
+    while (!iTask->complete) {
+        iscsi_set_events(iscsilun);
+        qemu_mutex_unlock(&iscsilun->mutex);
+        qemu_coroutine_yield();
+        qemu_mutex_lock(&iscsilun->mutex);
+    }
+}
+
 static int coroutine_fn
 iscsi_co_writev(BlockDriverState *bs, int64_t sector_num, int nb_sectors,
                 QEMUIOVector *iov, int flags)
@@ -616,12 +628,7 @@ retry:
     scsi_task_set_iov_out(iTask.task, (struct scsi_iovec *) iov->iov,
                           iov->niov);
 #endif
-    while (!iTask.complete) {
+    iscsi_co_wait_for_task(&iTask, iscsilun);
-        iscsi_set_events(iscsilun);
-        qemu_mutex_unlock(&iscsilun->mutex);
-        qemu_coroutine_yield();
-        qemu_mutex_lock(&iscsilun->mutex);
-    }
 
     if (iTask.task != NULL) {
         scsi_free_scsi_task(iTask.task);
@@ -692,13 +699,7 @@ retry:
         ret = -ENOMEM;
         goto out_unlock;
     }
-
+    iscsi_co_wait_for_task(&iTask, iscsilun);
-    while (!iTask.complete) {
-        iscsi_set_events(iscsilun);
-        qemu_mutex_unlock(&iscsilun->mutex);
-        qemu_coroutine_yield();
-        qemu_mutex_lock(&iscsilun->mutex);
-    }
 
     if (iTask.do_retry) {
         if (iTask.task != NULL) {
@@ -862,13 +863,8 @@ retry:
 #if LIBISCSI_API_VERSION < (20160603)
     scsi_task_set_iov_in(iTask.task, (struct scsi_iovec *) iov->iov, iov->niov);
 #endif
-    while (!iTask.complete) {
-        iscsi_set_events(iscsilun);
-        qemu_mutex_unlock(&iscsilun->mutex);
-        qemu_coroutine_yield();
-        qemu_mutex_lock(&iscsilun->mutex);
-    }
 
+    iscsi_co_wait_for_task(&iTask, iscsilun);
     if (iTask.task != NULL) {
         scsi_free_scsi_task(iTask.task);
         iTask.task = NULL;
@@ -905,12 +901,7 @@ retry:
         return -ENOMEM;
     }
 
-    while (!iTask.complete) {
+    iscsi_co_wait_for_task(&iTask, iscsilun);
-        iscsi_set_events(iscsilun);
-        qemu_mutex_unlock(&iscsilun->mutex);
-        qemu_coroutine_yield();
-        qemu_mutex_lock(&iscsilun->mutex);
-    }
 
     if (iTask.task != NULL) {
         scsi_free_scsi_task(iTask.task);
@@ -1142,12 +1133,7 @@ retry:
         goto out_unlock;
     }
 
-    while (!iTask.complete) {
+    iscsi_co_wait_for_task(&iTask, iscsilun);
-        iscsi_set_events(iscsilun);
-        qemu_mutex_unlock(&iscsilun->mutex);
-        qemu_coroutine_yield();
-        qemu_mutex_lock(&iscsilun->mutex);
-    }
 
     if (iTask.task != NULL) {
         scsi_free_scsi_task(iTask.task);
@@ -1243,12 +1229,7 @@ retry:
         return -ENOMEM;
     }
 
-    while (!iTask.complete) {
+    iscsi_co_wait_for_task(&iTask, iscsilun);
-        iscsi_set_events(iscsilun);
-        qemu_mutex_unlock(&iscsilun->mutex);
-        qemu_coroutine_yield();
-        qemu_mutex_lock(&iscsilun->mutex);
-    }
 
     if (iTask.status == SCSI_STATUS_CHECK_CONDITION &&
         iTask.task->sense.key == SCSI_SENSE_ILLEGAL_REQUEST &&
@@ -1740,6 +1721,30 @@ static QemuOptsList runtime_opts = {
     },
 };
 
+static void iscsi_save_designator(IscsiLun *lun,
+                                  struct scsi_inquiry_device_identification *inq_di)
+{
+    struct scsi_inquiry_device_designator *desig, *copy = NULL;
+
+    for (desig = inq_di->designators; desig; desig = desig->next) {
+        if (desig->association ||
+            desig->designator_type > SCSI_DESIGNATOR_TYPE_NAA) {
+            continue;
+        }
+        /* NAA works better than T10 vendor ID based designator. */
+        if (!copy || copy->designator_type < desig->designator_type) {
+            copy = desig;
+        }
+    }
+    if (copy) {
+        lun->dd = g_new(struct scsi_inquiry_device_designator, 1);
+        *lun->dd = *copy;
+        lun->dd->next = NULL;
+        lun->dd->designator = g_malloc(copy->designator_length);
+        memcpy(lun->dd->designator, copy->designator, copy->designator_length);
+    }
+}
+
 static int iscsi_open(BlockDriverState *bs, QDict *options, int flags,
                       Error **errp)
 {
@@ -1922,6 +1927,7 @@ static int iscsi_open(BlockDriverState *bs, QDict *options, int flags,
         struct scsi_task *inq_task;
         struct scsi_inquiry_logical_block_provisioning *inq_lbp;
         struct scsi_inquiry_block_limits *inq_bl;
+        struct scsi_inquiry_device_identification *inq_di;
         switch (inq_vpd->pages[i]) {
         case SCSI_INQUIRY_PAGECODE_LOGICAL_BLOCK_PROVISIONING:
             inq_task = iscsi_do_inquiry(iscsilun->iscsi, iscsilun->lun, 1,
@@ -1947,6 +1953,17 @@ static int iscsi_open(BlockDriverState *bs, QDict *options, int flags,
                    sizeof(struct scsi_inquiry_block_limits));
             scsi_free_scsi_task(inq_task);
             break;
+        case SCSI_INQUIRY_PAGECODE_DEVICE_IDENTIFICATION:
+            inq_task = iscsi_do_inquiry(iscsilun->iscsi, iscsilun->lun, 1,
+                                    SCSI_INQUIRY_PAGECODE_DEVICE_IDENTIFICATION,
+                                    (void **) &inq_di, errp);
+            if (inq_task == NULL) {
+                ret = -EINVAL;
+                goto out;
+            }
+            iscsi_save_designator(iscsilun, inq_di);
+            scsi_free_scsi_task(inq_task);
+            break;
         default:
             break;
         }
@@ -2003,6 +2020,10 @@ static void iscsi_close(BlockDriverState *bs)
         iscsi_logout_sync(iscsi);
     }
     iscsi_destroy_context(iscsi);
+    if (iscsilun->dd) {
+        g_free(iscsilun->dd->designator);
+        g_free(iscsilun->dd);
+    }
     g_free(iscsilun->zeroblock);
     iscsi_allocmap_free(iscsilun);
     qemu_mutex_destroy(&iscsilun->mutex);
@@ -2184,6 +2205,221 @@ static void coroutine_fn iscsi_co_invalidate_cache(BlockDriverState *bs,
     iscsi_allocmap_invalidate(iscsilun);
 }
 
+static int coroutine_fn iscsi_co_copy_range_from(BlockDriverState *bs,
+                                                 BdrvChild *src,
+                                                 uint64_t src_offset,
+                                                 BdrvChild *dst,
+                                                 uint64_t dst_offset,
+                                                 uint64_t bytes,
+                                                 BdrvRequestFlags flags)
+{
+    return bdrv_co_copy_range_to(src, src_offset, dst, dst_offset, bytes, flags);
+}
+
+static struct scsi_task *iscsi_xcopy_task(int param_len)
+{
+    struct scsi_task *task;
+
+    task = g_new0(struct scsi_task, 1);
+
+    task->cdb[0]     = EXTENDED_COPY;
+    task->cdb[10]    = (param_len >> 24) & 0xFF;
+    task->cdb[11]    = (param_len >> 16) & 0xFF;
+    task->cdb[12]    = (param_len >> 8) & 0xFF;
+    task->cdb[13]    = param_len & 0xFF;
+    task->cdb_size   = 16;
+    task->xfer_dir   = SCSI_XFER_WRITE;
+    task->expxferlen = param_len;
+
+    return task;
+}
+
+static void iscsi_populate_target_desc(unsigned char *desc, IscsiLun *lun)
+{
+    struct scsi_inquiry_device_designator *dd = lun->dd;
+
+    memset(desc, 0, 32);
+    desc[0] = 0xE4; /* IDENT_DESCR_TGT_DESCR */
+    desc[4] = dd->code_set;
+    desc[5] = (dd->designator_type & 0xF)
+        | ((dd->association & 3) << 4);
+    desc[7] = dd->designator_length;
+    memcpy(desc + 8, dd->designator, dd->designator_length);
+
+    desc[28] = 0;
+    desc[29] = (lun->block_size >> 16) & 0xFF;
+    desc[30] = (lun->block_size >> 8) & 0xFF;
+    desc[31] = lun->block_size & 0xFF;
+}
+
+static void iscsi_xcopy_desc_hdr(uint8_t *hdr, int dc, int cat, int src_index,
+                                 int dst_index)
+{
+    hdr[0] = 0x02; /* BLK_TO_BLK_SEG_DESCR */
+    hdr[1] = ((dc << 1) | cat) & 0xFF;
+    hdr[2] = (XCOPY_BLK2BLK_SEG_DESC_SIZE >> 8) & 0xFF;
+    /* don't account for the first 4 bytes in descriptor header*/
+    hdr[3] = (XCOPY_BLK2BLK_SEG_DESC_SIZE - 4 /* SEG_DESC_SRC_INDEX_OFFSET */) & 0xFF;
+    hdr[4] = (src_index >> 8) & 0xFF;
+    hdr[5] = src_index & 0xFF;
+    hdr[6] = (dst_index >> 8) & 0xFF;
+    hdr[7] = dst_index & 0xFF;
+}
+
+static void iscsi_xcopy_populate_desc(uint8_t *desc, int dc, int cat,
+                                      int src_index, int dst_index, int num_blks,
+                                      uint64_t src_lba, uint64_t dst_lba)
+{
+    iscsi_xcopy_desc_hdr(desc, dc, cat, src_index, dst_index);
+
+    /* The caller should verify the request size */
+    assert(num_blks < 65536);
+    desc[10] = (num_blks >> 8) & 0xFF;
+    desc[11] = num_blks & 0xFF;
+    desc[12] = (src_lba >> 56) & 0xFF;
+    desc[13] = (src_lba >> 48) & 0xFF;
+    desc[14] = (src_lba >> 40) & 0xFF;
+    desc[15] = (src_lba >> 32) & 0xFF;
+    desc[16] = (src_lba >> 24) & 0xFF;
+    desc[17] = (src_lba >> 16) & 0xFF;
+    desc[18] = (src_lba >> 8) & 0xFF;
+    desc[19] = src_lba & 0xFF;
+    desc[20] = (dst_lba >> 56) & 0xFF;
+    desc[21] = (dst_lba >> 48) & 0xFF;
+    desc[22] = (dst_lba >> 40) & 0xFF;
+    desc[23] = (dst_lba >> 32) & 0xFF;
+    desc[24] = (dst_lba >> 24) & 0xFF;
+    desc[25] = (dst_lba >> 16) & 0xFF;
+    desc[26] = (dst_lba >> 8) & 0xFF;
+    desc[27] = dst_lba & 0xFF;
+}
+
+static void iscsi_xcopy_populate_header(unsigned char *buf, int list_id, int str,
+                                        int list_id_usage, int prio,
+                                        int tgt_desc_len,
+                                        int seg_desc_len, int inline_data_len)
+{
+    buf[0] = list_id;
+    buf[1] = ((str & 1) << 5) | ((list_id_usage & 3) << 3) | (prio & 7);
+    buf[2] = (tgt_desc_len >> 8) & 0xFF;
+    buf[3] = tgt_desc_len & 0xFF;
+    buf[8] = (seg_desc_len >> 24) & 0xFF;
+    buf[9] = (seg_desc_len >> 16) & 0xFF;
+    buf[10] = (seg_desc_len >> 8) & 0xFF;
+    buf[11] = seg_desc_len & 0xFF;
+    buf[12] = (inline_data_len >> 24) & 0xFF;
+    buf[13] = (inline_data_len >> 16) & 0xFF;
+    buf[14] = (inline_data_len >> 8) & 0xFF;
+    buf[15] = inline_data_len & 0xFF;
+}
+
+static void iscsi_xcopy_data(struct iscsi_data *data,
+                             IscsiLun *src, int64_t src_lba,
+                             IscsiLun *dst, int64_t dst_lba,
+                             uint16_t num_blocks)
+{
+    uint8_t *buf;
+    const int src_offset = XCOPY_DESC_OFFSET;
+    const int dst_offset = XCOPY_DESC_OFFSET + IDENT_DESCR_TGT_DESCR_SIZE;
+    const int seg_offset = dst_offset + IDENT_DESCR_TGT_DESCR_SIZE;
+
+    data->size = XCOPY_DESC_OFFSET +
+                 IDENT_DESCR_TGT_DESCR_SIZE * 2 +
+                 XCOPY_BLK2BLK_SEG_DESC_SIZE;
+    data->data = g_malloc0(data->size);
+    buf = data->data;
+
+    /* Initialise the parameter list header */
+    iscsi_xcopy_populate_header(buf, 1, 0, 2 /* LIST_ID_USAGE_DISCARD */,
+                                0, 2 * IDENT_DESCR_TGT_DESCR_SIZE,
+                                XCOPY_BLK2BLK_SEG_DESC_SIZE,
+                                0);
+
+    /* Initialise CSCD list with one src + one dst descriptor */
+    iscsi_populate_target_desc(&buf[src_offset], src);
+    iscsi_populate_target_desc(&buf[dst_offset], dst);
+
+    /* Initialise one segment descriptor */
+    iscsi_xcopy_populate_desc(&buf[seg_offset], 0, 0, 0, 1, num_blocks,
+                              src_lba, dst_lba);
+}
+
+static int coroutine_fn iscsi_co_copy_range_to(BlockDriverState *bs,
+                                               BdrvChild *src,
+                                               uint64_t src_offset,
+                                               BdrvChild *dst,
+                                               uint64_t dst_offset,
+                                               uint64_t bytes,
+                                               BdrvRequestFlags flags)
+{
+    IscsiLun *dst_lun = dst->bs->opaque;
+    IscsiLun *src_lun;
+    struct IscsiTask iscsi_task;
+    struct iscsi_data data;
+    int r = 0;
+    int block_size;
+
+    if (src->bs->drv->bdrv_co_copy_range_to != iscsi_co_copy_range_to) {
+        return -ENOTSUP;
+    }
+    src_lun = src->bs->opaque;
+
+    if (!src_lun->dd || !dst_lun->dd) {
+        return -ENOTSUP;
+    }
+    if (!is_byte_request_lun_aligned(dst_offset, bytes, dst_lun)) {
+        return -ENOTSUP;
+    }
+    if (!is_byte_request_lun_aligned(src_offset, bytes, src_lun)) {
+        return -ENOTSUP;
+    }
+    if (dst_lun->block_size != src_lun->block_size ||
+        !dst_lun->block_size) {
+        return -ENOTSUP;
+    }
+
+    block_size = dst_lun->block_size;
+    if (bytes / block_size > 65535) {
+        return -ENOTSUP;
+    }
+
+    iscsi_xcopy_data(&data,
+                     src_lun, src_offset / block_size,
+                     dst_lun, dst_offset / block_size,
+                     bytes / block_size);
+
+    iscsi_co_init_iscsitask(dst_lun, &iscsi_task);
+
+    qemu_mutex_lock(&dst_lun->mutex);
+    iscsi_task.task = iscsi_xcopy_task(data.size);
+retry:
+    if (iscsi_scsi_command_async(dst_lun->iscsi, dst_lun->lun,
+                                 iscsi_task.task, iscsi_co_generic_cb,
+                                 &data,
+                                 &iscsi_task) != 0) {
+        r = -EIO;
+        goto out_unlock;
+    }
+
+    iscsi_co_wait_for_task(&iscsi_task, dst_lun);
+
+    if (iscsi_task.do_retry) {
+        iscsi_task.complete = 0;
+        goto retry;
+    }
+
+    if (iscsi_task.status != SCSI_STATUS_GOOD) {
+        r = iscsi_task.err_code;
+        goto out_unlock;
+    }
+
+out_unlock:
+    g_free(iscsi_task.task);
+    qemu_mutex_unlock(&dst_lun->mutex);
+    g_free(iscsi_task.err_str);
+    return r;
+}
+
 static QemuOptsList iscsi_create_opts = {
     .name = "iscsi-create-opts",
     .head = QTAILQ_HEAD_INITIALIZER(iscsi_create_opts.head),
@@ -2218,6 +2454,8 @@ static BlockDriver bdrv_iscsi = {
 
     .bdrv_co_block_status  = iscsi_co_block_status,
     .bdrv_co_pdiscard      = iscsi_co_pdiscard,
+    .bdrv_co_copy_range_from = iscsi_co_copy_range_from,
+    .bdrv_co_copy_range_to  = iscsi_co_copy_range_to,
     .bdrv_co_pwrite_zeroes = iscsi_co_pwrite_zeroes,
     .bdrv_co_readv         = iscsi_co_readv,
     .bdrv_co_writev        = iscsi_co_writev,
@@ -2253,6 +2491,8 @@ static BlockDriver bdrv_iser = {
 
     .bdrv_co_block_status  = iscsi_co_block_status,
     .bdrv_co_pdiscard      = iscsi_co_pdiscard,
+    .bdrv_co_copy_range_from = iscsi_co_copy_range_from,
+    .bdrv_co_copy_range_to  = iscsi_co_copy_range_to,
     .bdrv_co_pwrite_zeroes = iscsi_co_pwrite_zeroes,
     .bdrv_co_readv         = iscsi_co_readv,
     .bdrv_co_writev        = iscsi_co_writev,

block/qcow2.c

@@ -1761,6 +1761,39 @@ static int coroutine_fn qcow2_co_block_status(BlockDriverState *bs,
     return status;
 }
 
+static coroutine_fn int qcow2_handle_l2meta(BlockDriverState *bs,
+                                            QCowL2Meta **pl2meta,
+                                            bool link_l2)
+{
+    int ret = 0;
+    QCowL2Meta *l2meta = *pl2meta;
+
+    while (l2meta != NULL) {
+        QCowL2Meta *next;
+
+        if (!ret && link_l2) {
+            ret = qcow2_alloc_cluster_link_l2(bs, l2meta);
+            if (ret) {
+                goto out;
+            }
+        }
+
+        /* Take the request off the list of running requests */
+        if (l2meta->nb_clusters != 0) {
+            QLIST_REMOVE(l2meta, next_in_flight);
+        }
+
+        qemu_co_queue_restart_all(&l2meta->dependent_requests);
+
+        next = l2meta->next;
+        g_free(l2meta);
+        l2meta = next;
+    }
+out:
+    *pl2meta = l2meta;
+    return ret;
+}
+
 static coroutine_fn int qcow2_co_preadv(BlockDriverState *bs, uint64_t offset,
                                         uint64_t bytes, QEMUIOVector *qiov,
                                         int flags)
@@ -2047,24 +2080,9 @@ static coroutine_fn int qcow2_co_pwritev(BlockDriverState *bs, uint64_t offset,
             }
         }
 
-        while (l2meta != NULL) {
+        ret = qcow2_handle_l2meta(bs, &l2meta, true);
-            QCowL2Meta *next;
+        if (ret) {
-
+            goto fail;
-            ret = qcow2_alloc_cluster_link_l2(bs, l2meta);
-            if (ret < 0) {
-                goto fail;
-            }
-
-            /* Take the request off the list of running requests */
-            if (l2meta->nb_clusters != 0) {
-                QLIST_REMOVE(l2meta, next_in_flight);
-            }
-
-            qemu_co_queue_restart_all(&l2meta->dependent_requests);
-
-            next = l2meta->next;
-            g_free(l2meta);
-            l2meta = next;
         }
 
         bytes -= cur_bytes;
@@ -2075,18 +2093,7 @@ static coroutine_fn int qcow2_co_pwritev(BlockDriverState *bs, uint64_t offset,
     ret = 0;
 
 fail:
-    while (l2meta != NULL) {
+    qcow2_handle_l2meta(bs, &l2meta, false);
-        QCowL2Meta *next;
-
-        if (l2meta->nb_clusters != 0) {
-            QLIST_REMOVE(l2meta, next_in_flight);
-        }
-        qemu_co_queue_restart_all(&l2meta->dependent_requests);
-
-        next = l2meta->next;
-        g_free(l2meta);
-        l2meta = next;
-    }
 
     qemu_co_mutex_unlock(&s->lock);
 
@@ -3273,6 +3280,166 @@ static coroutine_fn int qcow2_co_pdiscard(BlockDriverState *bs,
     return ret;
 }
 
+static int coroutine_fn
+qcow2_co_copy_range_from(BlockDriverState *bs,
+                         BdrvChild *src, uint64_t src_offset,
+                         BdrvChild *dst, uint64_t dst_offset,
+                         uint64_t bytes, BdrvRequestFlags flags)
+{
+    BDRVQcow2State *s = bs->opaque;
+    int ret;
+    unsigned int cur_bytes; /* number of bytes in current iteration */
+    BdrvChild *child = NULL;
+    BdrvRequestFlags cur_flags;
+
+    assert(!bs->encrypted);
+    qemu_co_mutex_lock(&s->lock);
+
+    while (bytes != 0) {
+        uint64_t copy_offset = 0;
+        /* prepare next request */
+        cur_bytes = MIN(bytes, INT_MAX);
+        cur_flags = flags;
+
+        ret = qcow2_get_cluster_offset(bs, src_offset, &cur_bytes, &copy_offset);
+        if (ret < 0) {
+            goto out;
+        }
+
+        switch (ret) {
+        case QCOW2_CLUSTER_UNALLOCATED:
+            if (bs->backing && bs->backing->bs) {
+                int64_t backing_length = bdrv_getlength(bs->backing->bs);
+                if (src_offset >= backing_length) {
+                    cur_flags |= BDRV_REQ_ZERO_WRITE;
+                } else {
+                    child = bs->backing;
+                    cur_bytes = MIN(cur_bytes, backing_length - src_offset);
+                    copy_offset = src_offset;
+                }
+            } else {
+                cur_flags |= BDRV_REQ_ZERO_WRITE;
+            }
+            break;
+
+        case QCOW2_CLUSTER_ZERO_PLAIN:
+        case QCOW2_CLUSTER_ZERO_ALLOC:
+            cur_flags |= BDRV_REQ_ZERO_WRITE;
+            break;
+
+        case QCOW2_CLUSTER_COMPRESSED:
+            ret = -ENOTSUP;
+            goto out;
+            break;
+
+        case QCOW2_CLUSTER_NORMAL:
+            child = bs->file;
+            copy_offset += offset_into_cluster(s, src_offset);
+            if ((copy_offset & 511) != 0) {
+                ret = -EIO;
+                goto out;
+            }
+            break;
+
+        default:
+            abort();
+        }
+        qemu_co_mutex_unlock(&s->lock);
+        ret = bdrv_co_copy_range_from(child,
+                                      copy_offset,
+                                      dst, dst_offset,
+                                      cur_bytes, cur_flags);
+        qemu_co_mutex_lock(&s->lock);
+        if (ret < 0) {
+            goto out;
+        }
+
+        bytes -= cur_bytes;
+        src_offset += cur_bytes;
+        dst_offset += cur_bytes;
+    }
+    ret = 0;
+
+out:
+    qemu_co_mutex_unlock(&s->lock);
+    return ret;
+}
+
+static int coroutine_fn
+qcow2_co_copy_range_to(BlockDriverState *bs,
+                       BdrvChild *src, uint64_t src_offset,
+                       BdrvChild *dst, uint64_t dst_offset,
+                       uint64_t bytes, BdrvRequestFlags flags)
+{
+    BDRVQcow2State *s = bs->opaque;
+    int offset_in_cluster;
+    int ret;
+    unsigned int cur_bytes; /* number of sectors in current iteration */
+    uint64_t cluster_offset;
+    uint8_t *cluster_data = NULL;
+    QCowL2Meta *l2meta = NULL;
+
+    assert(!bs->encrypted);
+    s->cluster_cache_offset = -1; /* disable compressed cache */
+
+    qemu_co_mutex_lock(&s->lock);
+
+    while (bytes != 0) {
+
+        l2meta = NULL;
+
+        offset_in_cluster = offset_into_cluster(s, dst_offset);
+        cur_bytes = MIN(bytes, INT_MAX);
+
+        /* TODO:
+         * If src->bs == dst->bs, we could simply copy by incrementing
+         * the refcnt, without copying user data.
+         * Or if src->bs == dst->bs->backing->bs, we could copy by discarding. */
+        ret = qcow2_alloc_cluster_offset(bs, dst_offset, &cur_bytes,
+                                         &cluster_offset, &l2meta);
+        if (ret < 0) {
+            goto fail;
+        }
+
+        assert((cluster_offset & 511) == 0);
+
+        ret = qcow2_pre_write_overlap_check(bs, 0,
+                cluster_offset + offset_in_cluster, cur_bytes);
+        if (ret < 0) {
+            goto fail;
+        }
+
+        qemu_co_mutex_unlock(&s->lock);
+        ret = bdrv_co_copy_range_to(src, src_offset,
+                                    bs->file,
+                                    cluster_offset + offset_in_cluster,
+                                    cur_bytes, flags);
+        qemu_co_mutex_lock(&s->lock);
+        if (ret < 0) {
+            goto fail;
+        }
+
+        ret = qcow2_handle_l2meta(bs, &l2meta, true);
+        if (ret) {
+            goto fail;
+        }
+
+        bytes -= cur_bytes;
+        dst_offset += cur_bytes;
+    }
+    ret = 0;
+
+fail:
+    qcow2_handle_l2meta(bs, &l2meta, false);
+
+    qemu_co_mutex_unlock(&s->lock);
+
+    qemu_vfree(cluster_data);
+    trace_qcow2_writev_done_req(qemu_coroutine_self(), ret);
+
+    return ret;
+}
+
 static int qcow2_truncate(BlockDriverState *bs, int64_t offset,
                           PreallocMode prealloc, Error **errp)
 {
@@ -4521,6 +4688,8 @@ BlockDriver bdrv_qcow2 = {
 
     .bdrv_co_pwrite_zeroes  = qcow2_co_pwrite_zeroes,
     .bdrv_co_pdiscard       = qcow2_co_pdiscard,
+    .bdrv_co_copy_range_from = qcow2_co_copy_range_from,
+    .bdrv_co_copy_range_to  = qcow2_co_copy_range_to,
     .bdrv_truncate          = qcow2_truncate,
     .bdrv_co_pwritev_compressed = qcow2_co_pwritev_compressed,
     .bdrv_make_empty        = qcow2_make_empty,

block/raw-format.c

@@ -167,16 +167,37 @@ static void raw_reopen_abort(BDRVReopenState *state)
     state->opaque = NULL;
 }
 
+/* Check and adjust the offset, against 'offset' and 'size' options. */
+static inline int raw_adjust_offset(BlockDriverState *bs, uint64_t *offset,
+                                    uint64_t bytes, bool is_write)
+{
+    BDRVRawState *s = bs->opaque;
+
+    if (s->has_size && (*offset > s->size || bytes > (s->size - *offset))) {
+        /* There's not enough space for the write, or the read request is
+         * out-of-range. Don't read/write anything to prevent leaking out of
+         * the size specified in options. */
+        return is_write ? -ENOSPC : -EINVAL;;
+    }
+
+    if (*offset > INT64_MAX - s->offset) {
+        return -EINVAL;
+    }
+    *offset += s->offset;
+
+    return 0;
+}
+
 static int coroutine_fn raw_co_preadv(BlockDriverState *bs, uint64_t offset,
                                       uint64_t bytes, QEMUIOVector *qiov,
                                       int flags)
 {
-    BDRVRawState *s = bs->opaque;
+    int ret;
 
-    if (offset > UINT64_MAX - s->offset) {
+    ret = raw_adjust_offset(bs, &offset, bytes, false);
-        return -EINVAL;
+    if (ret) {
+        return ret;
     }
-    offset += s->offset;
 
     BLKDBG_EVENT(bs->file, BLKDBG_READ_AIO);
     return bdrv_co_preadv(bs->file, offset, bytes, qiov, flags);
@@ -186,23 +207,11 @@ static int coroutine_fn raw_co_pwritev(BlockDriverState *bs, uint64_t offset,
                                        uint64_t bytes, QEMUIOVector *qiov,
                                        int flags)
 {
-    BDRVRawState *s = bs->opaque;
     void *buf = NULL;
     BlockDriver *drv;
     QEMUIOVector local_qiov;
     int ret;
 
-    if (s->has_size && (offset > s->size || bytes > (s->size - offset))) {
-        /* There's not enough space for the data. Don't write anything and just
-         * fail to prevent leaking out of the size specified in options. */
-        return -ENOSPC;
-    }
-
-    if (offset > UINT64_MAX - s->offset) {
-        ret = -EINVAL;
-        goto fail;
-    }
-
     if (bs->probed && offset < BLOCK_PROBE_BUF_SIZE && bytes) {
         /* Handling partial writes would be a pain - so we just
          * require that guests have 512-byte request alignment if
@@ -237,7 +246,10 @@ static int coroutine_fn raw_co_pwritev(BlockDriverState *bs, uint64_t offset,
         qiov = &local_qiov;
     }
 
-    offset += s->offset;
+    ret = raw_adjust_offset(bs, &offset, bytes, true);
+    if (ret) {
+        goto fail;
+    }
 
     BLKDBG_EVENT(bs->file, BLKDBG_WRITE_AIO);
     ret = bdrv_co_pwritev(bs->file, offset, bytes, qiov, flags);
@@ -267,22 +279,24 @@ static int coroutine_fn raw_co_pwrite_zeroes(BlockDriverState *bs,
                                              int64_t offset, int bytes,
                                              BdrvRequestFlags flags)
 {
-    BDRVRawState *s = bs->opaque;
+    int ret;
-    if (offset > UINT64_MAX - s->offset) {
+
-        return -EINVAL;
+    ret = raw_adjust_offset(bs, (uint64_t *)&offset, bytes, true);
+    if (ret) {
+        return ret;
     }
-    offset += s->offset;
     return bdrv_co_pwrite_zeroes(bs->file, offset, bytes, flags);
 }
 
 static int coroutine_fn raw_co_pdiscard(BlockDriverState *bs,
                                         int64_t offset, int bytes)
 {
-    BDRVRawState *s = bs->opaque;
+    int ret;
-    if (offset > UINT64_MAX - s->offset) {
+
-        return -EINVAL;
+    ret = raw_adjust_offset(bs, (uint64_t *)&offset, bytes, true);
+    if (ret) {
+        return ret;
     }
-    offset += s->offset;
     return bdrv_co_pdiscard(bs->file->bs, offset, bytes);
 }
 
@@ -483,6 +497,36 @@ static int raw_probe_geometry(BlockDriverState *bs, HDGeometry *geo)
     return bdrv_probe_geometry(bs->file->bs, geo);
 }
 
+static int coroutine_fn raw_co_copy_range_from(BlockDriverState *bs,
+                                               BdrvChild *src, uint64_t src_offset,
+                                               BdrvChild *dst, uint64_t dst_offset,
+                                               uint64_t bytes, BdrvRequestFlags flags)
+{
+    int ret;
+
+    ret = raw_adjust_offset(bs, &src_offset, bytes, false);
+    if (ret) {
+        return ret;
+    }
+    return bdrv_co_copy_range_from(bs->file, src_offset, dst, dst_offset,
+                                   bytes, flags);
+}
+
+static int coroutine_fn raw_co_copy_range_to(BlockDriverState *bs,
+                                             BdrvChild *src, uint64_t src_offset,
+                                             BdrvChild *dst, uint64_t dst_offset,
+                                             uint64_t bytes, BdrvRequestFlags flags)
+{
+    int ret;
+
+    ret = raw_adjust_offset(bs, &dst_offset, bytes, true);
+    if (ret) {
+        return ret;
+    }
+    return bdrv_co_copy_range_to(src, src_offset, bs->file, dst_offset, bytes,
+                                 flags);
+}
+
 BlockDriver bdrv_raw = {
     .format_name          = "raw",
     .instance_size        = sizeof(BDRVRawState),
@@ -499,6 +543,8 @@ BlockDriver bdrv_raw = {
     .bdrv_co_pwrite_zeroes = &raw_co_pwrite_zeroes,
     .bdrv_co_pdiscard     = &raw_co_pdiscard,
     .bdrv_co_block_status = &raw_co_block_status,
+    .bdrv_co_copy_range_from = &raw_co_copy_range_from,
+    .bdrv_co_copy_range_to  = &raw_co_copy_range_to,
     .bdrv_truncate        = &raw_truncate,
     .bdrv_getlength       = &raw_getlength,
     .has_variable_length  = true,

configure

@@ -5170,6 +5170,20 @@ if test "$fortify_source" != "no"; then
   fi
 fi
 
+###############################################
+# Check if copy_file_range is provided by glibc
+have_copy_file_range=no
+cat > $TMPC << EOF
+#include <unistd.h>
+int main(void) {
+  copy_file_range(0, NULL, 0, NULL, 0, 0);
+  return 0;
+}
+EOF
+if compile_prog "" "" ; then
+    have_copy_file_range=yes
+fi
+
 ##########################################
 # check if struct fsxattr is available via linux/fs.h
 
@@ -6273,6 +6287,9 @@ fi
 if test "$have_fsxattr" = "yes" ; then
     echo "HAVE_FSXATTR=y" >> $config_host_mak
 fi
+if test "$have_copy_file_range" = "yes" ; then
+    echo "HAVE_COPY_FILE_RANGE=y" >> $config_host_mak
+fi
 if test "$vte" = "yes" ; then
   echo "CONFIG_VTE=y" >> $config_host_mak
   echo "VTE_CFLAGS=$vte_cflags" >> $config_host_mak

include/block/block.h

@@ -611,4 +611,36 @@ bool bdrv_can_store_new_dirty_bitmap(BlockDriverState *bs, const char *name,
  */
 void bdrv_register_buf(BlockDriverState *bs, void *host, size_t size);
 void bdrv_unregister_buf(BlockDriverState *bs, void *host);
+
+/**
+ *
+ * bdrv_co_copy_range:
+ *
+ * Do offloaded copy between two children. If the operation is not implemented
+ * by the driver, or if the backend storage doesn't support it, a negative
+ * error code will be returned.
+ *
+ * Note: block layer doesn't emulate or fallback to a bounce buffer approach
+ * because usually the caller shouldn't attempt offloaded copy any more (e.g.
+ * calling copy_file_range(2)) after the first error, thus it should fall back
+ * to a read+write path in the caller level.
+ *
+ * @src: Source child to copy data from
+ * @src_offset: offset in @src image to read data
+ * @dst: Destination child to copy data to
+ * @dst_offset: offset in @dst image to write data
+ * @bytes: number of bytes to copy
+ * @flags: request flags. Must be one of:
+ *         0 - actually read data from src;
+ *         BDRV_REQ_ZERO_WRITE - treat the @src range as zero data and do zero
+ *                               write on @dst as if bdrv_co_pwrite_zeroes is
+ *                               called. Used to simplify caller code, or
+ *                               during BlockDriver.bdrv_co_copy_range_from()
+ *                               recursion.
+ *
+ * Returns: 0 if succeeded; negative error code if failed.
+ **/
+int coroutine_fn bdrv_co_copy_range(BdrvChild *src, uint64_t src_offset,
+                                    BdrvChild *dst, uint64_t dst_offset,
+                                    uint64_t bytes, BdrvRequestFlags flags);
 #endif

include/block/block_int.h

@@ -204,6 +204,37 @@ struct BlockDriver {
     int coroutine_fn (*bdrv_co_pdiscard)(BlockDriverState *bs,
         int64_t offset, int bytes);
 
+    /* Map [offset, offset + nbytes) range onto a child of @bs to copy from,
+     * and invoke bdrv_co_copy_range_from(child, ...), or invoke
+     * bdrv_co_copy_range_to() if @bs is the leaf child to copy data from.
+     *
+     * See the comment of bdrv_co_copy_range for the parameter and return value
+     * semantics.
+     */
+    int coroutine_fn (*bdrv_co_copy_range_from)(BlockDriverState *bs,
+                                                BdrvChild *src,
+                                                uint64_t offset,
+                                                BdrvChild *dst,
+                                                uint64_t dst_offset,
+                                                uint64_t bytes,
+                                                BdrvRequestFlags flags);
+
+    /* Map [offset, offset + nbytes) range onto a child of bs to copy data to,
+     * and invoke bdrv_co_copy_range_to(child, src, ...), or perform the copy
+     * operation if @bs is the leaf and @src has the same BlockDriver.  Return
+     * -ENOTSUP if @bs is the leaf but @src has a different BlockDriver.
+     *
+     * See the comment of bdrv_co_copy_range for the parameter and return value
+     * semantics.
+     */
+    int coroutine_fn (*bdrv_co_copy_range_to)(BlockDriverState *bs,
+                                              BdrvChild *src,
+                                              uint64_t src_offset,
+                                              BdrvChild *dst,
+                                              uint64_t dst_offset,
+                                              uint64_t bytes,
+                                              BdrvRequestFlags flags);
+
     /*
      * Building block for bdrv_block_status[_above] and
      * bdrv_is_allocated[_above].  The driver should answer only
@@ -1102,4 +1133,11 @@ void bdrv_dec_in_flight(BlockDriverState *bs);
 
 void blockdev_close_all_bdrv_states(void);
 
+int coroutine_fn bdrv_co_copy_range_from(BdrvChild *src, uint64_t src_offset,
+                                         BdrvChild *dst, uint64_t dst_offset,
+                                         uint64_t bytes, BdrvRequestFlags flags);
+int coroutine_fn bdrv_co_copy_range_to(BdrvChild *src, uint64_t src_offset,
+                                       BdrvChild *dst, uint64_t dst_offset,
+                                       uint64_t bytes, BdrvRequestFlags flags);
+
 #endif /* BLOCK_INT_H */

include/block/raw-aio.h

@@ -25,9 +25,15 @@
 #define QEMU_AIO_FLUSH        0x0008
 #define QEMU_AIO_DISCARD      0x0010
 #define QEMU_AIO_WRITE_ZEROES 0x0020
+#define QEMU_AIO_COPY_RANGE   0x0040
 #define QEMU_AIO_TYPE_MASK \
-        (QEMU_AIO_READ|QEMU_AIO_WRITE|QEMU_AIO_IOCTL|QEMU_AIO_FLUSH| \
+        (QEMU_AIO_READ | \
-         QEMU_AIO_DISCARD|QEMU_AIO_WRITE_ZEROES)
+         QEMU_AIO_WRITE | \
+         QEMU_AIO_IOCTL | \
+         QEMU_AIO_FLUSH | \
+         QEMU_AIO_DISCARD | \
+         QEMU_AIO_WRITE_ZEROES | \
+         QEMU_AIO_COPY_RANGE)
 
 /* AIO flags */
 #define QEMU_AIO_MISALIGNED   0x1000

include/scsi/constants.h

@@ -311,4 +311,8 @@
 #define MMC_PROFILE_HDDVD_RW_DL         0x005A
 #define MMC_PROFILE_INVALID             0xFFFF
 
+#define XCOPY_DESC_OFFSET 16
+#define IDENT_DESCR_TGT_DESCR_SIZE 32
+#define XCOPY_BLK2BLK_SEG_DESC_SIZE 28
+
 #endif

include/sysemu/block-backend.h

@@ -232,4 +232,8 @@ void blk_set_force_allow_inactivate(BlockBackend *blk);
 void blk_register_buf(BlockBackend *blk, void *host, size_t size);
 void blk_unregister_buf(BlockBackend *blk, void *host);
 
+int coroutine_fn blk_co_copy_range(BlockBackend *blk_in, int64_t off_in,
+                                   BlockBackend *blk_out, int64_t off_out,
+                                   int bytes, BdrvRequestFlags flags);
+
 #endif

qemu-img.c

@@ -1547,6 +1547,7 @@ typedef struct ImgConvertState {
     bool compressed;
     bool target_has_backing;
     bool wr_in_order;
+    bool copy_range;
     int min_sparse;
     size_t cluster_sectors;
     size_t buf_sectors;
@@ -1740,6 +1741,37 @@ static int coroutine_fn convert_co_write(ImgConvertState *s, int64_t sector_num,
     return 0;
 }
 
+static int coroutine_fn convert_co_copy_range(ImgConvertState *s, int64_t sector_num,
+                                              int nb_sectors)
+{
+    int n, ret;
+
+    while (nb_sectors > 0) {
+        BlockBackend *blk;
+        int src_cur;
+        int64_t bs_sectors, src_cur_offset;
+        int64_t offset;
+
+        convert_select_part(s, sector_num, &src_cur, &src_cur_offset);
+        offset = (sector_num - src_cur_offset) << BDRV_SECTOR_BITS;
+        blk = s->src[src_cur];
+        bs_sectors = s->src_sectors[src_cur];
+
+        n = MIN(nb_sectors, bs_sectors - (sector_num - src_cur_offset));
+
+        ret = blk_co_copy_range(blk, offset, s->target,
+                                sector_num << BDRV_SECTOR_BITS,
+                                n << BDRV_SECTOR_BITS, 0);
+        if (ret < 0) {
+            return ret;
+        }
+
+        sector_num += n;
+        nb_sectors -= n;
+    }
+    return 0;
+}
+
 static void coroutine_fn convert_co_do_copy(void *opaque)
 {
     ImgConvertState *s = opaque;
@@ -1762,6 +1794,7 @@ static void coroutine_fn convert_co_do_copy(void *opaque)
         int n;
         int64_t sector_num;
         enum ImgConvertBlockStatus status;
+        bool copy_range;
 
         qemu_co_mutex_lock(&s->lock);
         if (s->ret != -EINPROGRESS || s->sector_num >= s->total_sectors) {
@@ -1791,7 +1824,9 @@ static void coroutine_fn convert_co_do_copy(void *opaque)
                                         s->allocated_sectors, 0);
         }
 
-        if (status == BLK_DATA) {
+retry:
+        copy_range = s->copy_range && s->status == BLK_DATA;
+        if (status == BLK_DATA && !copy_range) {
             ret = convert_co_read(s, sector_num, n, buf);
             if (ret < 0) {
                 error_report("error while reading sector %" PRId64
@@ -1813,7 +1848,15 @@ static void coroutine_fn convert_co_do_copy(void *opaque)
         }
 
         if (s->ret == -EINPROGRESS) {
-            ret = convert_co_write(s, sector_num, n, buf, status);
+            if (copy_range) {
+                ret = convert_co_copy_range(s, sector_num, n);
+                if (ret) {
+                    s->copy_range = false;
+                    goto retry;
+                }
+            } else {
+                ret = convert_co_write(s, sector_num, n, buf, status);
+            }
             if (ret < 0) {
                 error_report("error while writing sector %" PRId64
                              ": %s", sector_num, strerror(-ret));
@@ -1936,6 +1979,7 @@ static int img_convert(int argc, char **argv)
     ImgConvertState s = (ImgConvertState) {
         /* Need at least 4k of zeros for sparse detection */
         .min_sparse         = 8,
+        .copy_range         = true,
         .buf_sectors        = IO_BUF_SIZE / BDRV_SECTOR_SIZE,
         .wr_in_order        = true,
         .num_coroutines     = 8,
@@ -1976,6 +2020,7 @@ static int img_convert(int argc, char **argv)
             break;
         case 'c':
             s.compressed = true;
+            s.copy_range = false;
             break;
         case 'o':
             if (!is_valid_option_list(optarg)) {
@@ -2017,6 +2062,7 @@ static int img_convert(int argc, char **argv)
             }
 
             s.min_sparse = sval / BDRV_SECTOR_SIZE;
+            s.copy_range = false;
             break;
         }
         case 'p':

tests/qemu-iotests/common.filter

@@ -77,7 +77,6 @@ _filter_qemu()
 {
     sed -e "s#\\(^\\|(qemu) \\)$(basename $QEMU_PROG):#\1QEMU_PROG:#" \
         -e 's#^QEMU [0-9]\+\.[0-9]\+\.[0-9]\+ monitor#QEMU X.Y.Z monitor#' \
-        -e '/main-loop: WARNING: I\/O thread spun for [0-9]\+ iterations/d' \
         -e $'s#\r##' # QEMU monitor uses \r\n line endings
 }
 

util/main-loop.c

@@ -222,36 +222,11 @@ static int os_host_main_loop_wait(int64_t timeout)
 {
     GMainContext *context = g_main_context_default();
     int ret;
-    static int spin_counter;
 
     g_main_context_acquire(context);
 
     glib_pollfds_fill(&timeout);
 
-    /* If the I/O thread is very busy or we are incorrectly busy waiting in
-     * the I/O thread, this can lead to starvation of the BQL such that the
-     * VCPU threads never run.  To make sure we can detect the later case,
-     * print a message to the screen.  If we run into this condition, create
-     * a fake timeout in order to give the VCPU threads a chance to run.
-     */
-    if (!timeout && (spin_counter > MAX_MAIN_LOOP_SPIN)) {
-        static bool notified;
-
-        if (!notified && !qtest_enabled() && !qtest_driver()) {
-            warn_report("I/O thread spun for %d iterations",
-                        MAX_MAIN_LOOP_SPIN);
-            notified = true;
-        }
-
-        timeout = SCALE_MS;
-    }
-
-
-    if (timeout) {
-        spin_counter = 0;
-    } else {
-        spin_counter++;
-    }
     qemu_mutex_unlock_iothread();
     replay_mutex_unlock();